Why You Cannot Rank First: Modifications for Benchmarking Six-Degree-of-Freedom Visual Localization Algorithms
Sheng Han, Wei Gao, Zhanyi Hu · 2023
Read Why You Cannot Rank First: Modifications for Benchmarking Six-Degree-of-Freedom Visual Localization Algorithms by Sheng Han, Wei Gao, Zhanyi Hu (2023) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-10708860.txt.
Description
Benchmarks for visual localization can mislead rankings, Sheng Han, Wei Gao, and Zhanyi Hu argue in a 2023 paper. Robust, precise localization over long periods is a formidable challenge in spatial vision. Appearance changes with seasons and lighting, from dawn to night, and more datasets have emerged to test systems under those shifts, promoting progress for vehicles and handheld devices alike.
The manuscript aims to rectify limitations of the current public benchmark for long-term visual localization. That applies especially to the autonomous vehicle challenge. Vehicle data sets come from multi-camera rigs with fixed calibration and serialized image sequences, facts the benchmark should respect. Several modifications are proposed to make evaluation more rational and comprehensive. Readers get a fairer yardstick for six-degree-of-freedom localization.
Catalog record
| CREATOR | Sheng Han, Wei Gao, Zhanyi Hu |
|---|---|
| YEAR | 2023 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 49 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |